# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("buddhist-nlp/sanstib")
model = AutoModel.from_pretrained("buddhist-nlp/sanstib", device_map="auto")Quick Links
This model creates Sanskrit and Tibetan sentence embeddings and can be used for semantic similarity tasks. Sanskrit needs to be segmented first and converted into internal transliteration (I will upload the according script here soon). The Tibetan needs to be converted into wylie transliteration.
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="buddhist-nlp/sanstib")